Research Paper #833
|Singing Maps: Classification of Whalesong Units Using a Self-Organizing Feature Mapping Algorithm
|Walker,AV; Fisher,RB; Mitsakakis,N
|Submitted to the J. Acoustic Society of America
|A widespread problem in the study of humpback whale song vocalizations involves evaluating the similarity of song elements within a whale's repertoire, between individuals of a social group, and between social groups separated by time and space. Whilst humpback whale songs demonstrate a remarkable amount of regular high level structure, they are composed of a variety of complex and transient elemental phonological units. Reliable classification of song structure requires robust unit classification - a feature which has made this process difficult to automate. This work presents a fully automated technique for performing multiple-resolution classification. in this scheme, units are simultaneous assigned membership to a series of increasingly general acoustic classes such that degrees of song structural similarities (and differences) emerge from analysis of units classified at different resolutions.